Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    curiosity and inquiry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    એ
    0.66
    A
    0.57
    In
    0.56
    By
    0.56
     $\
    0.55
    i
    0.54
    Create
    0.54
    构建
    0.54
    Recognition
    0.53
    a
    0.53
    POSITIVE LOGITS
     ketua
    0.61
    tım
    0.61
     yeri
    0.60
    dır
    0.59
    )$.
    0.57
     emeritus
    0.56
     ؟
    0.55
    }$.
    0.55
    ײ
    0.52
    ,}
    0.52
    Act Density 0.033%

    No Known Activations